Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Selective Risk Control on ARC benchmark leaderboard · SOTA2 Research

Research Benchmarks

Selective Risk Control on ARC

0RiskCoFact

Updated 2mo ago

Evaluation Results

Method	Links
CoFact2026.05		0	0	0
Conf-Arbitrage2026.05		0	0	0
CSA2026.05		7.8	56.2	0

SOTA Paper

CoFact

Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs

Dataset

ARC

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Reinforcement Learning from Verifiable Rewards on HEAD-QA Distribution-shift Robustness on Sixteen Adversarial Cells MedQA + GSM8K (eval)Expert-Iteration RLVR on MedQA, HEAD-QA, ARC-C, and CaseHOLD Natural Language Inference on MedNLI Mathematical Reasoning on GSM8K (AR%, Risk%)